© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78139
    Prev
    Next
    INDEX
    Explanations

    snippets of information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ʖ
    -0.65
    RegistryLite
    -0.64
     AssemblyTitle
    -0.63
    awtextra
    -0.63
     jScrollPane
    -0.61
    Попис
    -0.59
     propOrder
    -0.56
    EndProject
    -0.54
    évaluateur
    -0.53
    glTexCoord
    -0.53
    POSITIVE LOGITS
    homa
    0.69
    hom
    0.57
    HOM
    0.52
    ho
    0.50
    hos
    0.48
     Lester
    0.43
    home
    0.43
    horn
    0.43
     onCancelled
    0.42
     Holiday
    0.42
    Activations Density 0.000%

    No Known Activations